# Learning Explainable Representations of Complex Game-playing Strategies

arXiv: https://arxiv.org/abs/2610.07638 · HTML: https://mlsanity.com/paper/2610.07638/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 61 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 4 of 4)

- [A Closer Look at Invalid Action Masking in Policy Gradient Algorithms](https://mlsanity.com/paper/2006.14171/) (2020)
- [Neural Programmer: Inducing Latent Programs with Gradient Descent](https://mlsanity.com/paper/1511.04834/) (2015)
- [What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies](https://mlsanity.com/paper/2203.11912/) (2022)
- [Program Synthesis Guided Reinforcement Learning for Partially Observed Environments](https://mlsanity.com/paper/2102.11137/) (2021)

## Abstract (arXiv)

As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules to improve their performance. These concepts are applied to explain other players' actions, and to inform their own actions in-game. Understanding other players' strategies is a crucial part of such improvement, but requires time and effort. In this paper, we propose a strategy similar to human cognition for training RL agents to synthesize learned strategies and policies as executable procedures based on sequences of gameplay actions. We present methods to automatically learn such programs to play chess and to solve tasks in a grid-based environment. We show that the learned strategies produce effective actions, and can be learned from gameplay data.